nadir / reports /train_log.json
ProCreations's picture
Nadir v2: element head, inner-page data, runtime fixes
864f427 verified
Raw History Blame Contribute Delete
6.58 kB
{
"args": {
"data": "ds_v2.pkl",
"out": "run_w",
"d": 384,
"layers": 8,
"heads": 6,
"epochs": 18,
"bs": 48,
"lr": 0.0003,
"wd": 0.05,
"drop": 0.1,
"native_weight": 0.5,
"seed": 0,
"workers": 5,
"elem_weight": 0.1,
"role_weight": 0.03,
"elem_balance": 0.3,
"init": "v1_best.pt"
},
"params": 16027747,
"log": [
{
"epoch": 0,
"step": 794,
"secs": 126,
"loss": 0.1623,
"dE": 0.04288,
"con": 0.03147,
"elem": 0.37817,
"e_ok": 0.94195,
"s0_dE": 0.04166,
"s0_dL": 0.03983,
"s0_con": 0.01493,
"e_acc": 0.87222,
"e_nll": 0.31791,
"r_acc": 0.74936,
"s1_dE": 0.11709,
"s1_dL": 0.11392,
"s1_con": 0.29847
},
{
"epoch": 1,
"step": 1588,
"secs": 246,
"loss": 0.14616,
"dE": 0.044,
"con": 0.03079,
"elem": 0.28204,
"e_ok": 0.94722,
"s0_dE": 0.04111,
"s0_dL": 0.03933,
"s0_con": 0.01486,
"e_acc": 0.88492,
"e_nll": 0.29707,
"r_acc": 0.76823,
"s1_dE": 0.11303,
"s1_dL": 0.10971,
"s1_con": 0.29463
},
{
"epoch": 2,
"step": 2382,
"secs": 371,
"loss": 0.14248,
"dE": 0.0433,
"con": 0.02879,
"elem": 0.2718,
"e_ok": 0.94794,
"s0_dE": 0.04045,
"s0_dL": 0.03863,
"s0_con": 0.01225,
"e_acc": 0.88913,
"e_nll": 0.28905,
"r_acc": 0.77894,
"s1_dE": 0.11051,
"s1_dL": 0.1072,
"s1_con": 0.26784
},
{
"epoch": 3,
"step": 3176,
"secs": 481,
"loss": 0.13929,
"dE": 0.04303,
"con": 0.0288,
"elem": 0.26188,
"e_ok": 0.94794,
"s0_dE": 0.04085,
"s0_dL": 0.03902,
"s0_con": 0.01576,
"e_acc": 0.88403,
"e_nll": 0.29122,
"r_acc": 0.78404,
"s1_dE": 0.12151,
"s1_dL": 0.118,
"s1_con": 0.13395
},
{
"epoch": 4,
"step": 3970,
"secs": 592,
"loss": 0.13736,
"dE": 0.04279,
"con": 0.029,
"elem": 0.25577,
"e_ok": 0.94722,
"s0_dE": 0.0397,
"s0_dL": 0.03794,
"s0_con": 0.01431,
"e_acc": 0.88994,
"e_nll": 0.29091,
"r_acc": 0.78723,
"s1_dE": 0.11205,
"s1_dL": 0.10875,
"s1_con": 0.24692
},
{
"epoch": 5,
"step": 4764,
"secs": 705,
"loss": 0.13486,
"dE": 0.04215,
"con": 0.0303,
"elem": 0.24835,
"e_ok": 0.95037,
"s0_dE": 0.03995,
"s0_dL": 0.03818,
"s0_con": 0.01163,
"e_acc": 0.89342,
"e_nll": 0.2904,
"r_acc": 0.78489,
"s1_dE": 0.10674,
"s1_dL": 0.1034,
"s1_con": 0.21942
},
{
"epoch": 6,
"step": 5558,
"secs": 816,
"loss": 0.13262,
"dE": 0.04164,
"con": 0.02965,
"elem": 0.24241,
"e_ok": 0.94998,
"s0_dE": 0.03888,
"s0_dL": 0.03715,
"s0_con": 0.01823,
"e_acc": 0.89142,
"e_nll": 0.29542,
"r_acc": 0.78795,
"s1_dE": 0.10818,
"s1_dL": 0.10477,
"s1_con": 0.13355
},
{
"epoch": 7,
"step": 6352,
"secs": 927,
"loss": 0.1297,
"dE": 0.04077,
"con": 0.02959,
"elem": 0.23773,
"e_ok": 0.94318,
"s0_dE": 0.03864,
"s0_dL": 0.03688,
"s0_con": 0.01412,
"e_acc": 0.88339,
"e_nll": 0.29541,
"r_acc": 0.7865,
"s1_dE": 0.10767,
"s1_dL": 0.10424,
"s1_con": 0.15202
},
{
"epoch": 8,
"step": 7146,
"secs": 1038,
"loss": 0.12712,
"dE": 0.0403,
"con": 0.02936,
"elem": 0.22914,
"e_ok": 0.94752,
"s0_dE": 0.03815,
"s0_dL": 0.03647,
"s0_con": 0.01527,
"e_acc": 0.89185,
"e_nll": 0.30129,
"r_acc": 0.78701,
"s1_dE": 0.10567,
"s1_dL": 0.10227,
"s1_con": 0.20398
},
{
"epoch": 9,
"step": 7940,
"secs": 1148,
"loss": 0.12518,
"dE": 0.0398,
"con": 0.0268,
"elem": 0.22563,
"e_ok": 0.94726,
"s0_dE": 0.03823,
"s0_dL": 0.03653,
"s0_con": 0.01809,
"e_acc": 0.88853,
"e_nll": 0.30672,
"r_acc": 0.78863,
"s1_dE": 0.10322,
"s1_dL": 0.09977,
"s1_con": 0.15727
},
{
"epoch": 10,
"step": 8734,
"secs": 1257,
"loss": 0.12307,
"dE": 0.03913,
"con": 0.02326,
"elem": 0.22178,
"e_ok": 0.94556,
"s0_dE": 0.03785,
"s0_dL": 0.03619,
"s0_con": 0.02286,
"e_acc": 0.88683,
"e_nll": 0.31044,
"r_acc": 0.78472,
"s1_dE": 0.0992,
"s1_dL": 0.09587,
"s1_con": 0.19078
},
{
"epoch": 11,
"step": 9528,
"secs": 1369,
"loss": 0.1209,
"dE": 0.03851,
"con": 0.02494,
"elem": 0.21819,
"e_ok": 0.94488,
"s0_dE": 0.03751,
"s0_dL": 0.03585,
"s0_con": 0.01708,
"e_acc": 0.88586,
"e_nll": 0.31137,
"r_acc": 0.79003,
"s1_dE": 0.09999,
"s1_dL": 0.09671,
"s1_con": 0.22857
},
{
"epoch": 12,
"step": 10322,
"secs": 1480,
"loss": 0.11961,
"dE": 0.03832,
"con": 0.02343,
"elem": 0.21455,
"e_ok": 0.94433,
"s0_dE": 0.03703,
"s0_dL": 0.03539,
"s0_con": 0.01577,
"e_acc": 0.88654,
"e_nll": 0.32437,
"r_acc": 0.78799,
"s1_dE": 0.10176,
"s1_dL": 0.09848,
"s1_con": 0.18905
},
{
"epoch": 13,
"step": 11116,
"secs": 1602,
"loss": 0.11784,
"dE": 0.03781,
"con": 0.02268,
"elem": 0.21099,
"e_ok": 0.94429,
"s0_dE": 0.03681,
"s0_dL": 0.03517,
"s0_con": 0.01501,
"e_acc": 0.88403,
"e_nll": 0.32853,
"r_acc": 0.78867,
"s1_dE": 0.09691,
"s1_dL": 0.09349,
"s1_con": 0.1905
},
{
"epoch": 14,
"step": 11910,
"secs": 1713,
"loss": 0.11638,
"dE": 0.03747,
"con": 0.02049,
"elem": 0.20897,
"e_ok": 0.94437,
"s0_dE": 0.03681,
"s0_dL": 0.03517,
"s0_con": 0.01695,
"e_acc": 0.88599,
"e_nll": 0.32894,
"r_acc": 0.78876,
"s1_dE": 0.10008,
"s1_dL": 0.09666,
"s1_con": 0.17253
},
{
"epoch": 15,
"step": 12704,
"secs": 1824,
"loss": 0.11504,
"dE": 0.03695,
"con": 0.02021,
"elem": 0.20677,
"e_ok": 0.94463,
"s0_dE": 0.03671,
"s0_dL": 0.03509,
"s0_con": 0.01521,
"e_acc": 0.88645,
"e_nll": 0.33489,
"r_acc": 0.78799,
"s1_dE": 0.09822,
"s1_dL": 0.09477,
"s1_con": 0.17304
},
{
"epoch": 16,
"step": 13498,
"secs": 1934,
"loss": 0.1141,
"dE": 0.03677,
"con": 0.02107,
"elem": 0.20373,
"e_ok": 0.94208,
"s0_dE": 0.03658,
"s0_dL": 0.03496,
"s0_con": 0.01736,
"e_acc": 0.88369,
"e_nll": 0.33225,
"r_acc": 0.78519,
"s1_dE": 0.09748,
"s1_dL": 0.09415,
"s1_con": 0.19973
},
{
"epoch": 17,
"step": 14292,
"secs": 2053,
"loss": 0.11284,
"dE": 0.03617,
"con": 0.02163,
"elem": 0.20522,
"e_ok": 0.94378,
"s0_dE": 0.03654,
"s0_dL": 0.03492,
"s0_con": 0.01713,
"e_acc": 0.88535,
"e_nll": 0.34029,
"r_acc": 0.78514,
"s1_dE": 0.09664,
"s1_dL": 0.09326,
"s1_con": 0.20492
}
],
"best_score": 0.0686828651548906
}